ReMe/reme4/config/default.yaml

service:
  backend: http
#  backend: mcp

jobs:
  - backend: base
    name: demo
    description: "demo job description"
    parameters:
      type: object
      properties:
        query:
          type: string
          description: "query"
        min_score:
          type: number
          description: "min score"
          default: 0.5
      required:
        - query
    steps:
      - backend: demo_echo_step1
      - backend: demo_echo_step2

  - backend: base
    name: version
    description: "return reme4 package version"
    parameters:
      type: object
      properties: {}
    steps:
      - backend: version_step

  - backend: base
    name: health_check
    description: "return a concise health-check snapshot of reme4 components"
    parameters:
      type: object
      properties: {}
    steps:
      - backend: health_check_step

  - backend: base
    name: help
    description: "list all registered jobs with their metadata"
    parameters:
      type: object
      properties: {}
    steps:
      - backend: help_step

  - backend: base
    name: reindex
    description: "wipe the file store and rebuild it from the watcher's tracked files"
    parameters:
      type: object
      properties: {}
    steps:
      - backend: reindex_step

  - backend: base
    name: search
    description: "hybrid search over file_store: vector + keyword fused via RRF"
    parameters:
      type: object
      properties:
        query:
          type: string
          description: "search query"
        limit:
          type: integer
          description: "max results to return"
          default: 5
        min_score:
          type: number
          description: "minimum fused score threshold (RRF scores are small; default 0 disables filter)"
          default: 0.0
        vector_weight:
          type: number
          description: "weight for vector results in [0, 1]; keyword weight = 1 - vector_weight"
          default: 0.7
        candidate_multiplier:
          type: number
          description: "candidate pool multiplier per branch (capped at 200)"
          default: 3.0
        expand_links:
          type: boolean
          description: "attach outlinks/inlinks (with neighbor meta) to each result"
          default: true
        max_links_per_direction:
          type: integer
          description: "max neighbors shown per direction per result"
          default: 10
      required:
        - query
    steps:
      - backend: search_step

  - backend: base
    name: read
    description: "read a markdown file (relative path under working_dir)"
    parameters:
      type: object
      properties:
        path:
          type: string
          description: "relative path under the working_dir (no absolute paths); markdown only"
        start_line:
          type: integer
          description: "Optional, first line to read (1-based, inclusive)"
        end_line:
          type: integer
          description: "Optional, last line to read (1-based, inclusive)"
      required:
        - path
    steps:
      - backend: read_step

  - backend: stream
    name: stream_demo
    description: "stream demo job: repeat query 10x and stream char-by-char"
    parameters:
      type: object
      properties:
        query:
          type: string
          description: "query to echo"
        repeat:
          type: integer
          description: "number of times to repeat the query"
          default: 10
        interval:
          type: number
          description: "seconds between chunks"
          default: 0.1
      required:
        - query
    steps:
      - backend: stream_demo_step1
      - backend: stream_demo_step2

components:
  # 1. tokenizer — no dependencies
  tokenizer:
    default:
      backend: regex

  # 2. embedding_model — no dependencies
  embedding_model:
    default:
      backend: openai
      model_name: text-embedding-v4
      dimensions: 1024

  # 3. file_graph — no dependencies
  file_graph:
    default:
      backend: local

  # 4. file_parser — no dependencies
  file_parser:
    default:
      backend: default

  # 5. keyword_index — depends on tokenizer
  keyword_index:
    default:
      backend: bm25
      tokenizer: default

  # 6. file_store — depends on embedding_model / keyword_index / file_graph
  file_store:
    default:
      backend: local
      store_name: default
#      embedding_model: default
      embedding_model: ""
      keyword_index: default
      file_graph: default

  # 7. file_watcher — depends on file_store / file_parser
  file_watcher:
    default:
      backend: lite
      watch_paths:
        - MEMORY.md
        - memory
      file_store: default
      file_parser: default